Free cookie consent management tool by TermsFeed Policy Generator

Changeset 14780 for trunk/sources


Ignore:
Timestamp:
03/23/17 10:47:04 (8 years ago)
Author:
gkronber
Message:

#2755: set dataset partitions correctly in GBT with logistic regression loss

File:
1 edited

Legend:

Unmodified
Added
Removed
  • trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs

    r14779 r14780  
    255255          var classificationProblemData = new ClassificationProblemData(problemData.Dataset,
    256256            problemData.AllowedInputVariables, problemData.TargetVariable, problemData.Transformations);
     257          classificationProblemData.TrainingPartition.Start = Problem.ProblemData.TrainingPartition.Start;
     258          classificationProblemData.TrainingPartition.End = Problem.ProblemData.TrainingPartition.End;
     259          classificationProblemData.TestPartition.Start = Problem.ProblemData.TestPartition.Start;
     260          classificationProblemData.TestPartition.End = Problem.ProblemData.TestPartition.End;
     261
    257262          classificationModel.SetThresholdsAndClassValues(new double[] { double.NegativeInfinity, 0.0 }, new []{ 0.0, 1.0 });
     263
    258264
    259265          var classificationSolution = new DiscriminantFunctionClassificationSolution(classificationModel, classificationProblemData);
Note: See TracChangeset for help on using the changeset viewer.